Screenshot
Captures screenshots and performs OCR text recognition using two engines, with Japanese and English support.
About
Screenshot captures areas of the screen and uses OCR to recognize text. It uses yomitoku as its primary OCR engine for high-accuracy Japanese text recognition, and Tesseract.js as a fallback engine for both Japanese and English. The tool provides multiple output formats including JSON, Markdown, vertical, and horizontal. This server can be configured to work with Claude desktop by modifying the `claude_desktop_config.json` file.
Key Features
- Screenshot capture (left half, right half, full screen)
- OCR text recognition (Japanese and English)
- Multiple output formats (JSON, Markdown, vertical, horizontal)
- Uses yomitoku for high-accuracy Japanese OCR
- Uses Tesseract.js as a fallback OCR engine
Use Cases
- Automating text extraction from screenshots
- Integrating OCR functionality with Claude desktop
- Quickly capturing and processing text from screen captures
Sponsored